© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    how can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīä¸ĢçĤ¹
    -0.10
    пл
    -0.09
    å¾ģæĪĺ
    -0.09
    olist
    -0.09
    oster
    -0.08
    èijĽ
    -0.08
    åħ¸åŀĭçļĦ
    -0.08
     Notebook
    -0.08
    reich
    -0.08
    ÑĤÑĥÑĢ
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.17
    è¿Ļä¹Īå¤ļ
    0.16
    è¿Ļä¹Ī
    0.13
    å¦ĤæѤ
    0.13
    è¿Ļä¹Īä¹ħ
    0.12
    è¿Ļä¹Īå¤ļå¹´
    0.12
    è¿ĻèĪ¬
    0.12
    éĤ£ä¹Ī容æĺĵ
    0.11
    æĿĸ
    0.11
    è¿Ļä¹Ī大
    0.11
    Activations Density 0.108%

    No Known Activations